About the job
Datadog’s APM Experiences team owns the core product experience for Application Performance Monitoring — including distributed tracing, service representation, and more. We’re building a new wave of AI-powered capabilities that help customers detect, resolve, and prevent performance issues faster. In this role, you will lead end‑to‑end development of LLM- and Agent‑based features that can: Debug and investigate application performance issues down to the root cause, as both a developer assistant and a fully autonomous agent; Proactively recommend performance and reliability-based optimizations to prevent the next incident; Automatically create intelligent monitors and SLOs for the most important business flows and critical paths. This is a highly product‑minded engineering role: you’ll work from problem discovery and UX all the way to reliable, scalable production systems.
Responsibilities
Shape AI experiences for APM. Design and ship LLM/agentic workflows that analyze traces, metrics, logs, and other telemetry to generate diagnoses, explanations, and guided fixes.
Own the full loop. Prototype quickly, define success metrics and evals, run experiments, iterate, and ultimately productionize for scale and reliability.
Build robust agent systems. Develop tools, retrieval and planning strategies, and guardrails; manage prompts/evals; design fallbacks and human‑in‑the‑loop paths.
Integrate with Datadog’s platform. Leverage surfaces like Trace Explorer, Service Catalog, monitors, and workflows to deliver end‑to‑end value in the APM UI.
Partner deeply. Collaborate with PM, Design, and partner teams to build cohesive experiences.
Raise the bar on engineering. Write performant, maintainable backend code, own services in production, and improve reliability for high‑throughput, low‑latency data systems.
Qualifications
Minimum
4+ years building backend or real-time ML systems; you value simplicity, correctness, and performance
Proven experience delivering LLM/agent features to production (prompting, tooling, evals, safety/guardrails)
Comfortable owning user journeys, iterating from prototype → alpha → GA, and measuring impact with clear product metrics
You have demonstrated ability to use AI coding tools in day-to-day workflows and validate, critique, and refine AI-generated output
You’re motivated to push the boundaries of how AI can improve software engineering best practices and contribute to building AI-enabled products
Solid grasp of the ML lifecycle (task definition, dataset collection, modeling, evaluation, deployment, iteration) and statistics (experiment design, confidence intervals)
Experience choosing/modeling the right technique for the job (e.g., anomaly detection, ranking/recommendation, NLP), and knowing when a heuristic beats a model
Fluency with offline/online evals for AI systems; can build reliable golden sets and automatic regressions
Experience with microservices performance: tracing, latency breakdowns, concurrency, and resiliency patterns
Proficient in Go, Java, or Python; strong API/service design; production ops (monitoring, alerting, on‑call rotation)
Preferred
Hands‑on with distributed tracing stacks (OpenTelemetry/Datadog APM), profilers, and logs/metrics pipelines
Exposure to planning/agent frameworks, tool‑use orchestration, RAG, and retrieval/indexing for observability data
Familiarity with SLO/SLA practices and incident response